Wu Shuo learned that Tether recently showcased its newly launched QVAC system, successfully running the LLAMA 3.2 (1 billion parameters) model on mobile devices with llama.cpp, achieving efficient local inference. QVAC is a universal inference and fine-tuning runtime designed to adapt to various terminal devices, including smartphones, laptops, and servers. It currently supports multiple models and will expand to support more models in the future. https://www. (wublock123.com)/index.php? m=content&c=index&a=show&catid=6&id=45836